CN105744345B - Video-frequency compression method and device - Google Patents

Video-frequency compression method and device Download PDF

Info

Publication number
CN105744345B
CN105744345B CN201410767813.3A CN201410767813A CN105744345B CN 105744345 B CN105744345 B CN 105744345B CN 201410767813 A CN201410767813 A CN 201410767813A CN 105744345 B CN105744345 B CN 105744345B
Authority
CN
China
Prior art keywords
frame
video file
video
file
moving target
Prior art date
Application number
CN201410767813.3A
Other languages
Chinese (zh)
Other versions
CN105744345A (en
Inventor
王甜甜
江中央
Original Assignee
深圳Tcl新技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳Tcl新技术有限公司 filed Critical 深圳Tcl新技术有限公司
Priority to CN201410767813.3A priority Critical patent/CN105744345B/en
Publication of CN105744345A publication Critical patent/CN105744345A/en
Application granted granted Critical
Publication of CN105744345B publication Critical patent/CN105744345B/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/85Assembly of content; Generation of multimedia applications
    • H04N21/854Content authoring
    • H04N21/8549Creating video summaries, e.g. movie trailer
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed circuit television systems, i.e. systems in which the signal is not broadcast

Abstract

The invention discloses a kind of video-frequency compression methods, comprising the following steps: extracts the I frame in video source file, obtains I-frame video file;Processing is filtered to the I-frame video file, obtains the effective video file for meeting setting condition;Multiplexed compressed processing is carried out to the effective video file, generates compressed video file.The invention also discloses a kind of devices for compressing video.Present invention reduces the times for reading analysis video, meanwhile, compressed video file size is reduced, the memory headroom size that compressed video file occupies is reduced.

Description

Video-frequency compression method and device

Technical field

The present invention relates to technical field of video processing more particularly to a kind of video-frequency compression methods and device.

Background technique

With the continuous improvement of computer technology, digital media technology, Online Video monitoring technology, video reads compression skill Art is widely used, and is acted on also more and more important.Video read compress technique be obtained by camera it is all Video simultaneously reads all videos of compression, and the video for reading compression includes the I frame (I-frames) of video, P frame (P-frames) With B frame (B-frames).It is read in compression process carrying out video, it is necessary first to read all video frames in video, then right Each frame video is analyzed in all video frames, in particular it is required that reading the foreground image and background image in video, and right All foreground images are analyzed in video, moving object all in foreground image are extracted, then by all of extraction Moving object sequence saves in memory, finally by these moving object sequence reorganizations to summarized radio space, to reach video The effect of compression.But due to needing to read the moving object in all video frames in carrying out video reading compression, and to institute There is the moving object in video frame to be analyzed, it is therefore desirable to the time for reading analysis is longer, and computation complexity is high, and after compressing Video also saved in memory due to having compressed all video frames, some insignificant information, therefore, cause compressed The memory that video occupies is very big, and the requirement to hardware is very high.

Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill Art.

Summary of the invention

It is a primary object of the present invention to solve video read read in compression analysis time is longer, compressed video Excessive technical problem.

To achieve the above object, a kind of video-frequency compression method provided by the invention, the described method comprises the following steps:

The I frame in video source file is extracted, I-frame video file is obtained;

Processing is filtered to the I-frame video file, obtains the effective video file for meeting setting condition;

Multiplexed compressed processing is carried out to the effective video file, generates compressed video file.

Preferably, the step of I frame extracted in video source file, acquisition I-frame video file specifically:

The video source file is decomposed into I frame using Deplexing method, the frame group video file that B frame is combined with P frame, mentioned The I frame in the frame group video file is taken, I-frame video file is formed.

Preferably, described that processing is filtered to the I-frame video file, obtain the effective video text for meeting setting condition The step of part includes:

According to several I frame images of the I-frame video file generated;

First I frame image of generation is handled, initial background frame image is obtained;

Each I frame image and the initial background frame image subtraction that first I frame image is generated later, acquisition pair Answer several moving targets in I frame image;

Face datection is carried out to each moving target, the corresponding I frame of moving target for not having face picture is abandoned, it will The corresponding I frame of moving target with face picture is saved;

Effective video file is generated according to the corresponding I frame of the moving target with face picture of preservation.

Preferably, the step of I frame images several according to the I-frame video file generated specifically:

Processing is decoded to the I-frame video file using decoder, generates YUV/RGB video file;Utilize coding Device carries out coded treatment to the YUV/RGB video file of generation, generates several I frame images.

Preferably, described the step of Face datection is carried out to each moving target specifically:

Detect in each moving target whether there is face picture using Adaboost algorithm.

In addition, to achieve the above object, the present invention also provides a kind of device for compressing video, described device includes:

Extraction module obtains I-frame video file for extracting the I frame in video source file;

Filtering module obtains the effective video for meeting setting condition for being filtered processing to the I-frame video file File;

Compression module generates compressed video file for carrying out multiplexed compressed processing to the effective video file.

Preferably, the extraction module is specifically used for:

The video source file is decomposed into I frame using Deplexing method, the frame group video file that B frame is combined with P frame, mentioned The I frame in the frame group video file is taken, I-frame video file is formed.

Preferably, the filtering module includes:

I frame image generation unit, for according to several I frame images of the I-frame video file generated;

Initial background frame image acquisition unit is handled for first I frame image to generation, obtains initial background Frame image;

Moving target acquiring unit, each I frame image for that will generate after first I frame image and described initial Background frames image subtraction obtains several moving targets in corresponding I frame image;

Face datection unit will not have the movement mesh of face picture for carrying out Face datection to each moving target It marks corresponding I frame to abandon, the corresponding I frame of moving target with face picture is saved;

Effective video file generating unit, it is raw for the corresponding I frame of the moving target with face picture according to preservation At effective video file.

Preferably, the I frame image generation unit is specifically used for:

Processing is decoded to the I-frame video file using decoder, generates YUV/RGB video file;Utilize coding Device carries out coded treatment to the YUV/RGB video file of generation, generates several I frame images.

Preferably, the Face datection unit is also used to:

Detect in each moving target whether there is face picture using Adaboost algorithm.

A kind of video-frequency compression method and device proposed by the present invention do not depend on other frames using I frame in video, are to deposit at random The point taken, while being this advantage of decoded reference frame, when reading video, the I frame in video source file is only extracted, is removed superfluous Remaining B frame and P frame forms I-frame video file, and is filtered processing to the I-frame video file and obtains effective video file, The effective video file is compressed to achieve the effect that video compress again, in this way, due to only extracting in video source file I frame be read out and analyze, highly shortened the time for reading analysis, meanwhile, reduce compressed video file Size reduces the memory headroom size that compressed video file occupies.

Detailed description of the invention

Fig. 1 is the flow diagram of one embodiment of video-frequency compression method of the present invention;

Fig. 2 is the refinement flow diagram of step S20 in Fig. 1;

Fig. 3 is the functional block diagram of one embodiment of device of present invention compression video;

Fig. 4 is the refinement the functional block diagram of filtering module 02 in Fig. 3.

The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.

Specific embodiment

It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.

The present invention provides a kind of video-frequency compression method.

Referring to Fig.1, Fig. 1 is the flow diagram of one embodiment of video-frequency compression method of the present invention.

In one embodiment, which includes:

Step S10 extracts the I frame in video source file, obtains I-frame video file;

In the present embodiment, video source file can be the video file got in real time by camera, be also possible to pre- The video file first stored, is not limited thereto.It, will be described using demultiplexing (demux) method after getting video source file Video source file is decomposed into the frame group video file of I frame (I-frames), P frame (P-frames) and B frame (B-frames) combination, Wherein, I frame is also key frame, it is the important frame in interframe compression coding;It is the coded frame of full frame compression;When decoding Only with the data of I frame with regard to restructural complete image;I frame is generated without necessarily referring to other pictures.I.e. I frame does not depend on other frames, It is random-access point, while is also decoded reference frame.After the video source file is decomposed, the frame group video is only extracted I frame in file removes the B frame and P frame of redundancy, forms I-frame video file.In this way, the characteristics of using I frame, can sufficiently read The video frame that can embody the video source file characteristic in video source file completely is taken, and can remove from and read extra B frame and P frame Process shortens the read access time of video source file, can read useful video frame faster.

Step S20 is filtered processing to the I-frame video file, obtains the effective video file for meeting setting condition;

Processing is filtered to the I-frame video file obtained from video source file using image processing algorithm, it is available Various detection algorithms in image processing algorithm detect the frame image in I-frame video file, for example, using image at Image segmentation and image zooming-out in adjustment method detect the image in the I-frame video file, are filtered, extract symbol Setting condition namely the I frame comprising useful information are closed, to get the effective video file for meeting setting condition.

Step S30 carries out multiplexed compressed processing to the effective video file, generates compressed video file.

(remux) compression processing is multiplexed to the effective video file for meeting setting condition got, generates compression Video file, to realize the purpose for compressing video source file.

The present embodiment does not depend on other frames using I frame in video, is random-access point, at the same be decoded reference frame this One advantage only extracts the I frame in video source file when reading video, removes the B frame and P frame of redundancy, forms I-frame video text Part, and processing is filtered to the I-frame video file and obtains effective video file, then the effective video file is pressed Contracting is to achieve the effect that video compress, in this way, being read out and analyzing due to only extracting the I frame in video source file, greatly Ground shortens the time for reading analysis, meanwhile, compressed video file size is reduced, compressed video file is reduced The memory headroom size of occupancy.

Specifically, as shown in Fig. 2, above-mentioned steps S20 may include:

Step S201, according to several I frame images of the I-frame video file generated;

The I frame in the frame group video file is extracted, after forming I-frame video file, using decoder (decode) to institute It states I-frame video file and is decoded processing, generate YUV/RGB video file, wherein YUV and RGB is color space, is used for Indicate color;It recycles encoder (encode) to carry out coded treatment to the YUV/RGB video file of generation, generates several I frames Image, wherein I frame image is I frame.

Step S202 handles first I frame image of generation, obtains initial background frame image;

Gaussian Background modeling side in image processing algorithm is utilized to the first I frame image generated in several I frame images Method handles it, obtains initial background frame image.

Step S203, by each the I frame image generated after first I frame image and the initial background frame image phase Subtract, obtains several moving targets in corresponding I frame image;

By each the I frame image generated after first I frame image in several I frame images with the initial background of acquisition Frame image subtraction obtains several moving targets in corresponding I frame image.

Step S204 carries out Face datection to each moving target, will not have the corresponding I of moving target of face picture Frame abandons, and the corresponding I frame of moving target with face picture is saved;

Face datection is carried out to each moving target using Adaboost algorithm, wherein Adaboost algorithm is face Whether a kind of detection algorithm, being detected in each moving target by Adaboost algorithm has face picture.When detecting one When not having face picture in moving target, then the moving target is judged for useless image information, then by the moving target pair The I frame answered abandons;When detecting has face picture in a moving target, then judge that the moving target is believed for useful image Breath, the corresponding I frame of the moving target is saved.

Step S205 generates effective video file according to the corresponding I frame of the moving target with face picture of preservation.

After carrying out Face datection to each moving target by Adaboost algorithm, there is several according to preservation face to draw The corresponding I frame of the moving target in face generates effective video file.In this way, due to all having carried out face inspection to each moving target It surveys, the processing of filtering screening, filters out the corresponding I frame of useless moving target without face picture, what is finally obtained has Imitating in video information is the corresponding I frame of useful moving target with face picture, avoids the interference of garbage, makes It is smaller to obtain the memory that effective video file occupies, fundamentally further reduces and is finally compressed with effective video file Compressed video file size afterwards reduces the memory headroom size that compressed video file occupies.

The present invention further provides a kind of devices for compressing video.

It should be noted that the device of the compression video can be TV, computer, mobile terminal in the embodiment of the present invention Deng the video playback apparatus with playing function, or video processing equipment relevant to video monitoring does not limit herein It is fixed.

Referring to the functional block diagram for one embodiment of device that Fig. 3, Fig. 3 are present invention compression video.

In one embodiment, the device of the compression video includes:

Extraction module 01 obtains I-frame video file for extracting the I frame in video source file;

In the present embodiment, video source file can be the video file got in real time by camera, be also possible to pre- The video file first stored, is not limited thereto.It, will be described using demultiplexing (demux) method after getting video source file Video source file is decomposed into the frame group video file of I frame (I-frames), P frame (P-frames) and B frame (B-frames) combination, Wherein, I frame is also key frame, it is the important frame in interframe compression coding;It is the coded frame of full frame compression;When decoding Only with the data of I frame with regard to restructural complete image;I frame is generated without necessarily referring to other pictures.I.e. I frame does not depend on other frames, It is random-access point, while is also decoded reference frame.After the video source file is decomposed, the frame group video is only extracted I frame in file removes the B frame and P frame of redundancy, forms I-frame video file.In this way, the characteristics of using I frame, can sufficiently read The video frame that can embody the video source file characteristic in video source file completely is taken, and can remove from and read extra B frame and P frame Process shortens the read access time of video source file, can read useful video frame faster.

Filtering module 02 obtains the effective view for meeting setting condition for being filtered processing to the I-frame video file Frequency file;

Processing is filtered to the I-frame video file obtained from video source file using image processing algorithm, it is available Various detection algorithms in image processing algorithm detect the frame image in I-frame video file, for example, using image at Image segmentation and image zooming-out in adjustment method detect the image in the I-frame video file, are filtered, extract symbol Setting condition namely the I frame comprising useful information are closed, to get the effective video file for meeting setting condition.

Compression module 03 generates compressed video file for carrying out multiplexed compressed processing to the effective video file.

(remux) compression processing is multiplexed to the effective video file for meeting setting condition got, generates compression Video file, to realize the purpose for compressing video source file.

The present embodiment does not depend on other frames using I frame in video, is random-access point, at the same be decoded reference frame this One advantage only extracts the I frame in video source file when reading video, removes the B frame and P frame of redundancy, forms I-frame video text Part, and processing is filtered to the I-frame video file and obtains effective video file, then the effective video file is pressed Contracting is to achieve the effect that video compress, in this way, being read out and analyzing due to only extracting the I frame in video source file, greatly Ground shortens the time for reading analysis, meanwhile, compressed video file size is reduced, compressed video file is reduced The memory headroom size of occupancy.

Specifically, as shown in figure 4, above-mentioned filtering module 02 may include:

I frame image generation unit 021, for according to several I frame images of the I-frame video file generated;

Initial background frame image acquisition unit 022 is handled for first I frame image to generation, is obtained initial Background frames image;

Moving target acquiring unit 023, each I frame image for that will generate after first I frame image with it is described Initial background frame image subtraction obtains several moving targets in corresponding I frame image;

Face datection unit 024 will not have the movement of face picture for carrying out Face datection to each moving target The corresponding I frame of target abandons, and the corresponding I frame of moving target with face picture is saved;

Effective video file generating unit 025, for the corresponding I frame of the moving target with face picture according to preservation Generate effective video file.

Specifically, the I frame in the frame group video file is extracted, after forming I-frame video file, utilizes decoder (decode) processing is decoded to the I-frame video file, generates YUV/RGB video file, wherein YUV and RGB is color Color space, for indicating color;Encoder (encode) is recycled to carry out coded treatment to the YUV/RGB video file of generation, Generate several I frame images, wherein I frame image is I frame.

Gaussian Background modeling side in image processing algorithm is utilized to the first I frame image generated in several I frame images Method handles it, obtains initial background frame image.It is each by being generated after first I frame image in several I frame images A I frame image with the initial background frame image subtraction of acquisition, obtains several moving targets in corresponding I frame image, then and first Each the I frame image namely I frame generated after a I frame image is corresponding with a moving target.

Face datection is carried out to each moving target using Adaboost algorithm, wherein Adaboost algorithm is face Whether a kind of detection algorithm, being detected in each moving target by Adaboost algorithm has face picture.When detecting one When not having face picture in moving target, then the moving target is judged for useless image information, then by the moving target pair The I frame answered abandons;When detecting has face picture in a moving target, then judge that the moving target is believed for useful image Breath, the corresponding I frame of the moving target is saved.

After carrying out Face datection to each moving target by Adaboost algorithm, there is several according to preservation face to draw The corresponding I frame of the moving target in face generates effective video file.In this way, due to all having carried out face inspection to each moving target It surveys, the processing of filtering screening, filters out the corresponding I frame of useless moving target without face picture, what is finally obtained has Imitating in video information is the corresponding I frame of useful moving target with face picture, avoids the interference of garbage, makes It is smaller to obtain the memory that effective video file occupies, fundamentally further reduces and is finally compressed with effective video file Compressed video file size afterwards reduces the memory headroom size that compressed video file occupies.

The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.Pass through above embodiment party The description of formula, it is required general that those skilled in the art can be understood that above-described embodiment method can add by software The mode of hardware platform is realized, naturally it is also possible to which by hardware, but in many cases, the former is more preferably embodiment.It is based on Such understanding, substantially the part that contributes to existing technology can be with software product in other words for technical solution of the present invention Form embody, which is stored in a storage medium (such as ROM/RAM, magnetic disk, CD), including Some instructions are used so that a terminal device (can be mobile phone, computer, server or the network equipment etc.) executes this hair Method described in bright each embodiment.

The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills Art field, is included within the scope of the present invention.

Claims (8)

1. a kind of video-frequency compression method, which is characterized in that the described method comprises the following steps:
The I frame in video source file is extracted, I-frame video file is obtained;
Processing is filtered to the I-frame video file, obtains the effective video file for meeting setting condition;
Multiplexed compressed processing is carried out to the effective video file, generates compressed video file;
It is described that processing is filtered to the I-frame video file, obtain the step of meeting the effective video file of setting condition packet It includes:
According to several I frame images of the I-frame video file generated;
First I frame image of generation is handled, initial background frame image is obtained;
Each the I frame image and the initial background frame image subtraction that will be generated after first I frame image obtain corresponding I Several moving targets in frame image;
Face datection is carried out to each moving target, the corresponding I frame of moving target for not having face picture is abandoned, will be had The corresponding I frame of the moving target of face picture is saved;
Effective video file is generated according to the corresponding I frame of the moving target with face picture of preservation.
2. video-frequency compression method as described in claim 1, which is characterized in that the I frame extracted in video source file obtains The step of I-frame video file specifically:
The video source file is decomposed into I frame using Deplexing method, the frame group video file that B frame is combined with P frame, extracts institute The I frame in frame group video file is stated, I-frame video file is formed.
3. video-frequency compression method as claimed in claim 1 or 2, which is characterized in that described according to the I-frame video file generated The step of several I frame images specifically:
Processing is decoded to the I-frame video file using decoder, generates YUV/RGB video file;Utilize encoder pair The YUV/RGB video file of generation carries out coded treatment, generates several I frame images.
4. video-frequency compression method as claimed in claim 1 or 2, which is characterized in that described to carry out face to each moving target The step of detection specifically:
Detect in each moving target whether there is face picture using Adaboost algorithm.
5. a kind of device for compressing video, which is characterized in that described device includes:
Extraction module obtains I-frame video file for extracting the I frame in video source file;
Filtering module obtains the effective video text for meeting setting condition for being filtered processing to the I-frame video file Part;
Compression module generates compressed video file for carrying out multiplexed compressed processing to the effective video file;
Wherein, the filtering module includes:
I frame image generation unit, for according to several I frame images of the I-frame video file generated;
Initial background frame image acquisition unit is handled for first I frame image to generation, obtains initial background frame figure Picture;
Moving target acquiring unit, each I frame image and the initial background for will be generated after first I frame image Frame image subtraction obtains several moving targets in corresponding I frame image;
Face datection unit will not have the moving target pair of face picture for carrying out Face datection to each moving target The I frame answered abandons, and the corresponding I frame of moving target with face picture is saved;
Effective video file generating unit has for the corresponding I frame generation of the moving target with face picture according to preservation Imitate video file.
6. device as claimed in claim 5, which is characterized in that the extraction module is specifically used for:
The video source file is decomposed into I frame using Deplexing method, the frame group video file that B frame is combined with P frame, extracts institute The I frame in frame group video file is stated, I-frame video file is formed.
7. such as device described in claim 5 or 6, which is characterized in that the I frame image generation unit is specifically used for:
Processing is decoded to the I-frame video file using decoder, generates YUV/RGB video file;Utilize encoder pair The YUV/RGB video file of generation carries out coded treatment, generates several I frame images.
8. such as device described in claim 5 or 6, which is characterized in that the Face datection unit is also used to:
Detect in each moving target whether there is face picture using Adaboost algorithm.
CN201410767813.3A 2014-12-12 2014-12-12 Video-frequency compression method and device CN105744345B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410767813.3A CN105744345B (en) 2014-12-12 2014-12-12 Video-frequency compression method and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410767813.3A CN105744345B (en) 2014-12-12 2014-12-12 Video-frequency compression method and device
PCT/CN2014/094012 WO2016090652A1 (en) 2014-12-12 2014-12-17 Video compression method and device

Publications (2)

Publication Number Publication Date
CN105744345A CN105744345A (en) 2016-07-06
CN105744345B true CN105744345B (en) 2019-05-31

Family

ID=56106515

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410767813.3A CN105744345B (en) 2014-12-12 2014-12-12 Video-frequency compression method and device

Country Status (2)

Country Link
CN (1) CN105744345B (en)
WO (1) WO2016090652A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108040282A (en) * 2017-12-21 2018-05-15 山东亿海兰特通信科技有限公司 A kind of video broadcasting method and device
CN108965740B (en) * 2018-07-11 2020-10-30 深圳超多维科技有限公司 Real-time video face changing method, device, equipment and storage medium
CN109167977B (en) * 2018-10-28 2020-10-23 广州中元软件有限公司 Bionic long-term storage method for surveillance video

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004208076A (en) * 2002-12-25 2004-07-22 Mitsubishi Electric Corp Signal generator unit for detecting video image, video image detection signal recorder unit, video signal regenerator unit, and methods for the units method of video image detection signal generation, video image detection signal recording and video signal regeneration
CN102075739A (en) * 2010-09-15 2011-05-25 深圳市九洲电器有限公司 Method and device for smoothly playing fast-forward/fast-rewind played network videos
CN102521578A (en) * 2011-12-19 2012-06-27 中山爱科数字科技股份有限公司 Method for detecting and identifying intrusion
CN103096028A (en) * 2011-11-02 2013-05-08 中国移动通信集团公司 Method and device for wireless video monitoring
CN103092930A (en) * 2012-12-30 2013-05-08 信帧电子技术(北京)有限公司 Method of generation of video abstract and device of generation of video abstract
US20130251033A1 (en) * 2012-03-26 2013-09-26 Electronics And Telecommunications Research Institute Method of compressing video frame using dual object extraction and object trajectory information in video encoding and decoding process

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20030026529A (en) * 2001-09-26 2003-04-03 엘지전자 주식회사 Keyframe Based Video Summary System
US20070237225A1 (en) * 2006-03-30 2007-10-11 Eastman Kodak Company Method for enabling preview of video files
JP4775306B2 (en) * 2007-04-23 2011-09-21 ソニー株式会社 Image processing apparatus, imaging apparatus, image display control method, and computer program
KR101335518B1 (en) * 2007-04-27 2013-12-03 삼성전자주식회사 Moving image displaying method and image replaying apparatus using the same
CN102156707A (en) * 2011-02-01 2011-08-17 刘中华 Video abstract forming and searching method and system
CN102810208B (en) * 2012-07-24 2015-12-16 武汉大千信息技术有限公司 Based on the criminal investigation video pre-filtering method that direct of travel detects

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004208076A (en) * 2002-12-25 2004-07-22 Mitsubishi Electric Corp Signal generator unit for detecting video image, video image detection signal recorder unit, video signal regenerator unit, and methods for the units method of video image detection signal generation, video image detection signal recording and video signal regeneration
CN102075739A (en) * 2010-09-15 2011-05-25 深圳市九洲电器有限公司 Method and device for smoothly playing fast-forward/fast-rewind played network videos
CN103096028A (en) * 2011-11-02 2013-05-08 中国移动通信集团公司 Method and device for wireless video monitoring
CN102521578A (en) * 2011-12-19 2012-06-27 中山爱科数字科技股份有限公司 Method for detecting and identifying intrusion
US20130251033A1 (en) * 2012-03-26 2013-09-26 Electronics And Telecommunications Research Institute Method of compressing video frame using dual object extraction and object trajectory information in video encoding and decoding process
CN103092930A (en) * 2012-12-30 2013-05-08 信帧电子技术(北京)有限公司 Method of generation of video abstract and device of generation of video abstract

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
从MPEG压缩视频流中提取I帧的设计与实现;石迎生,徐重阳等;《有线电视技术》;20030723(第14期);全文

Also Published As

Publication number Publication date
WO2016090652A1 (en) 2016-06-16
CN105744345A (en) 2016-07-06

Similar Documents

Publication Publication Date Title
Sadek et al. Video steganography: a comprehensive review
Barni et al. Aligned and non-aligned double JPEG detection using convolutional neural networks
JP5373909B2 (en) CABAC / AVC compliant watermarking of syntax elements in compressed video
Chen et al. Automatic detection of object-based forgery in advanced video
US8649431B2 (en) Method and apparatus for encoding and decoding image by using filtered prediction block
CA2615299C (en) Image encoding device, image decoding device, image encoding method, and image decoding method
Sitara et al. Digital video tampering detection: An overview of passive techniques
Milani et al. An overview on video forensics
KR101369915B1 (en) Video identifier extracting device
CN1265321C (en) Method of and system for detecting cartoon in video data stream
Liu et al. Image compression with edge-based inpainting
EP2357826A2 (en) Image encoding device, image decoding device, image encoding method, and image decoding method
JP4951521B2 (en) Video fingerprint system, method, and computer program product
CN106797479A (en) Prediction limitation is replicated for the intra block of parallel processing
CN106068527A (en) Depth perception for stereo data strengthens
Singh et al. Video content authentication techniques: a comprehensive survey
Rabie et al. High-capacity steganography: a global-adaptive-region discrete cosine transform approach
Shanableh Detection of frame deletion for digital video forensics
KR20090101910A (en) Banding artifact detection in digital video content
Zhang et al. Low-rank-based nonlocal adaptive loop filter for high-efficiency video compression
US8594449B2 (en) MPEG noise reduction
US20100080472A1 (en) Image processing apparatus, moving image decoding apparatus, moving image encoding apparatus and method
Yeh et al. Self-learning-based post-processing for image/video deblocking via sparse representation
Balle et al. Models for static and dynamic texture synthesis in image and video compression
Cheddad et al. Enhancing Steganography in digital images

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant